# robots.txt for cc4.marketing
# Allow all search engines and AI bots to crawl

# Default: Allow all bots
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_astro/
Disallow: /og-preview
Disallow: /og/preview.png
Disallow: /og/debug

# Google
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

# Bing
User-agent: Bingbot
Allow: /

User-agent: MSNBot
Allow: /

# Other major search engines
User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# AI Bots - Allow for training and indexing
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Social media crawlers
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterest
Allow: /

# Sitemap location
Sitemap: https://cc4.marketing/sitemap-index.xml

# LLMs.txt for AI agent discovery
LLMs-txt: https://cc4.marketing/llms.txt

# Crawl-delay (be nice to servers, but we want fast indexing)
# Most bots ignore this, but it's good practice
User-agent: *
Crawl-delay: 1

# Host directive (helps with canonical domain)
Host: https://cc4.marketing